Liquid AI releases LFM2.5-Encoder-230M and 350M bidirectional encoders, fastest CPU inference at long context
Original title:LFM2.5-Encoders: Fast at Long Context, Even on CPU
AI summary
Liquid AI releases LFM2.5-Encoder-230M and LFM2.5-Encoder-350M, two bidirectional encoders based on the LFM2 hybrid architecture that support an 8,192-token context and are available for download on Hugging Face.
Key Takeaways
- Liquid AI releases LFM2.
- 5-Encoder-230M and LFM2.
- 5-Encoder-350M,two bidirectional encoders based on the LFM2 hybrid architecture that support an…
Quick Facts
- Published
- Updated
- Source
- Liquid AI 模型与工程博客(网页)
- Category
- Model Releases
- AI score
- 65
原文给出双向编码器的架构改动、17 项任务微调评测和长上下文 CPU 吞吐对比,读者可以据此评估其在边缘和本地部署中的适用性。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Liquid AI releases LFM2.5-Encoder-230M and 350M bidirectional encoders, fastest CPU inference at long context. July 28, 2026. https://new.nat6.net/en/news/cmtym3yoy0006ronz5pdd728v/